Hi,
Immediate Hiring
Role Summary :
We are seeking a skilled Python Engineer to support the development and validation of Generative AI systems. The ideal candidate will work on integrating and customizing
the Guardrail library to enforce safety, reliability, and compliance in GenAI outputs. You will also design and implement robust test and validation scripts, particularly for
Retrieval-Augmented Generation (RAG) pipelines.

Key Responsibilities:

• Develop and maintain Python scripts for testing and validating GenAI models.
• Build the the Guardrail library to enforce output constraints and safety checks.
• Design validation frameworks for RAG-based GenAI systems.
• Collaborate with AI Governance team and product teams t
• Strong proficiency in Python.
• Hands-on experience with Generative AI, especially RAG architectures.
• Familiarity with LLM evaluation techniques and safety frameworks such as Guardrail AI, Llama Guard..etc
• Experience with libraries like LangChain, LlamaIndex, or similar is a plus.
• Knowledge of prompt engineering and model governance is desirable.

Requirements:

• More than 1 year of experience on Gen AI Engineering, more than 3 years of experience on AI Engineering is preferable.
• Strong proficiency in Python.
• Hands-on experience with Generative AI, especially RAG architectures.
• Familiarity with LLM evaluation techniques and safety frameworks.
• Experience with libraries like LangChain, LlamaIndex, or similar is a plus.
• Knowledge of prompt engineering and model governance is desirable.

Regards
Kshama
+91 9833964181
kshama.raj@blueocean.system

• Develop and maintain Python scripts for testing and validating GenAI models.
• Build the the Guardrail library to enforce output constraints and safety checks.
• Design validation frameworks for RAG-based GenAI systems.
• Collaborate with AI Governance team and product teams t
• Strong proficiency in Python.
• Hands-on experience with Generative AI, especially RAG architectures.
• Familiarity with LLM evaluation techniques and safety frameworks such as Guardrail AI, Llama Guard..etc
• Experience with libraries like LangChain, LlamaIndex, or similar is a plus.
• Knowledge of prompt engineering and model governance is desirable